1 / 22

Programming Model Support for Dependable, Elastic Cloud Applications

This paper discusses the critical need for elasticity and dependability in cloud applications. It highlights how naive approaches to elasticity can increase system failure rates, particularly in large systems prone to single node failures that can lead to global failures. We propose a programming model that supports dependable cloud applications by integrating mechanisms for flexible execution and enhanced fault tolerance. Our findings underscore the significance of context-aware elasticity in managing the complexities of cloud architectures, ensuring recovery from failures, and maintaining operational efficiency.

hei
Télécharger la présentation

Programming Model Support for Dependable, Elastic Cloud Applications

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Programming Model Support for Dependable, Elastic Cloud Applications Wei-Chiu Chuang, Bo Sang, Charles Killian, MilindKulkarni

  2. Motivation Elasticity Dependability Implementation Conclusion

  3. Motivation – Cloud in Reality

  4. Motivation -“Ideal” Cloud

  5. Motivation - Failures Failure! Single node failure induces global failure recovery

  6. Motivation – Failure in Large Systems Naïve elasticity makes system more likely to fail

  7. Motivation - Too Big To Fail

  8. Motivation Elasticity Dependability Implementation Conclusion

  9. Elasticity – Context Node state X Y Z = 5 e2 e1 e3 = 2 = 4

  10. Elasticity – Independent Contexts Commit in sequential order Node state X Y Z Context 1: x Context 2: y e2 e1 e3 Context 3: z

  11. Elasticity - Hierarchical Contexts e1 global e2 message c’ message message c

  12. Elasticity – Logical Node throughput Demands Distribute contexts to more nodes demand

  13. Elasticity – Logical Node throughput demand

  14. Elasticity – Logical Node throughput Elasticity: change the mapping of contexts to physical nodes demand

  15. Motivation Elasticity Dependability Implementation Conclusion

  16. Partial Recovery Failure recovery is per-context basis Failure! 3 2 1

  17. Event Replay Event replay is safe: outgoing messages is deferred until commit Failure! 3 2 1

  18. Motivation Elasticity Dependability Implementation Conclusion

  19. Head Node Logical node1 Remote nodes interact with head nodes Logical node3 Logical node2

  20. Motivation Elasticity Dependability Implementation Conclusion

  21. Conclusion • Elasticity is crucial for cloud applications. • Our programming model enables elastic execution. • The elastic mechanism also helps fault tolerance. MaceSystems http://www.macesystems.org

  22. Questions?

More Related